Next-gen senotherapeutics: AI/ML-driven strategies for aging and age-related disorders.

Abstract

Senotherapeutics comprising senolytics and senostats/senomorphs of natural and synthetic origin are powerful pharmacological interventions to combat aging and age-related disorders (ARD): cancer, HIV, diabetes, and neurodegenerative diseases. STs are novel strategies in the geroscience arena selectively targeting senescent cells responsible for unhealthy aging and ARD. The absence of specific biomarkers, gaps in integrating molecular mechanisms, and inadequate therapeutic drugs hamper translating the results from bench to bedside. Current innovations suggested to advance the field include machine learning, omics-based approaches, nanocarriers, molecularly imprinted nanoparticles, CART cells, and monoclonal antibodies. This book chapter will focus on STs interrupting molecular pathways involving senescent cells, SASPs, and immune cells in preclinical and clinical settings. Also, the chapter will highlight applications of AI/ML/DL tools like Random Forest, Support Vector Machines, phenotypic screening, neural networks, and predictive modeling for discovering STs to expedite the translation of preclinical findings to clinical applications. Despite challenges to obtaining quality data and model interpretability, the future of ML in senotherapeutics holds great promise in promoting longevity.